Abstract: An approach for optimizing storage on a local storage device. The approach receives a cloud resource budget limit and a cloud budget time interval. The approach estimates future cloud resource requests expected to arrive before the end of the cloud budget time interval. The approach calculates definitive and estimated costs of cloud resource usage types. The approach calculates a total estimated resource budget consumption. The approach determines if the total estimated resource budget consumption exceeds the cloud resource budget limit. If the approach determines the cloud resource budget limit is not exceeded, then the approach outputs a set of existing unfulfilled cloud resource requests for fulfillment. If the approach determines the cloud resource budget limit is exceeded, then the approach outputs a subset of set of existing unfulfilled cloud resource requests that do not exceed the cloud resource budget limit for fulfillment.

Abstract: Methods and systems are described herein for a resource allocation system. The resource allocation system may obtain a corresponding quantity of resources (e.g., memory, processor, storage, etc.) needed to be allocated for each resource class (e.g., for a given performance class) for a particular time period (e.g., for one month). Furthermore, the resource allocation system may track allocation of each class of resources and may predict that some classes of resources will be oversubscribed. Based on the prediction, the resource allocation system may, using a machine learning model, identify supplemental classes for each resource class predicted to be oversubscribed and generate a warning when a resource of a supplemental class is predicted to be used.

Abstract: A computer-implemented method, a computer program product, and a computer system for determining optimal data access for deep learning applications on a cluster. A server determines candidate cache locations for one or more compute nodes in the cluster. The server fetches a mini-batch of a dataset located at a remote storage service into the candidate cache locations. The server collects information about time periods of completing a job on the one or more nodes, where the job is executed against fetched mini-batch at the candidate cache locations and the mini-batch at the remote storage location. The server selects, from the candidate cache locations and the remote storage location, a cache location. The server fetches the data of the dataset from the remote storage service to the cache location, and the one or more nodes execute the job against fetched data of the dataset at the cache location.

Abstract: A system for recommending and optimizing artificial intelligence (AI) workload placement in a multi-vendor cloud environment is disclosed. The system utilizes a server with at least one processor to access input datasets stored in a datacentre associated with an AI workload and determine suitable processing units from various manufacturers based on predefined criteria. It calculates the required number of processing units and accesses a multi-vendor performance database. A deep learning model predicts infrastructure requirements for the AI workload, enabling the generation of recommendations for optimal processing unit configuration. The system automatically allocates processing unit resources from multiple manufacturers based on these recommendations. Finally, it generates data for a user interface dashboard, presenting information about manufacturers, processing unit types, recommended configurations, and real-time performance metrics of allocated resources.

Abstract: The present disclosure relates to systems, methods, and computer-readable media for deploying cloud-native services across a plurality of cloud-computing platforms. For example, systems disclosed herein identify resource identifiers associated with cloud-computing services (e.g., types of services) to be deployed on one or more resources capable of executing or otherwise providing cloud-native services. The systems disclosed herein further generate resource bindings including deployment specifications that include data for deploying cloud-native services on corresponding platform resources (e.g., cloud resources, edge resources). Using the resource bindings, the systems disclosed herein can deploy cloud-native services across multiple platforms via control planes configured to manage operation of resources on the different platforms.

Abstract: A system receives job requests comprising associated job names and associated job parameters. The system performs a comparison of a job name and parameters for a first, second, and third job request with information of previously performed jobs and determines a first, second, and third amount of memory to perform the job requests. The system evaluates the first, second, and third amounts of memory with predetermined memory sizes to determine if the memory amounts exceed the predetermined memory sizes. The system negotiates with schedulers from one or more service provider networks to allocate memory from temporary memories for each amount of memory that exceeds the predetermined memory sizes. The system creates a prioritized queue comprising the first, second, and third received job requests for scheduler processing based upon the amounts of memory. The system can use a trained algorithmic model to predict the first, second, and third amounts of memories.

Abstract: A method for allocation metering for virtual machines and containers includes gathering virtual structure (“VS”) allocation data for one or more virtual structures running on one or more servers at a customer location of a customer. a virtual structure includes a virtual machine (“VM”) or a container. The VS allocation data is for a virtual structure of the one or more virtual structures that include allocation of virtual resources for the virtual structure. The customer leases computing resources from an owner. The method includes periodically transmitting VS allocation data to an owner server of the owner over a management network different than a computer network servicing workloads of the virtual structures. The owner server is located off-premises from the customer location. Billing information is calculated at the owner server from the VS allocation data and includes a cost for virtual resources allocated to the virtual structures for the billing period.

Abstract: Disclosed are a method and system for managing a hybrid Spark cluster for efficient Spark job execution. A cluster management method which is performed by a cluster management system may include, in a hybrid Spark cluster environment including a bare-metal-based cluster and a Kubernetes-based cluster, selecting a cluster manager comprising the bare-metal-based cluster or the Kubernetes-based cluster before a Spark client performs a Spark driver program, and performing a Spark job by using the selected cluster manager.

Abstract: In some aspects, techniques may include monitoring a primary load of a datacenter and a reserve load of the datacenter. The primary load and reserve load can be monitored by a computing device. The primary load of the datacenter can be configured to be powered by one or more primary generator blocks having a primary capacity, and the reserve load of the datacenter can be configured to be powered by one or more reserve generator blocks having a reserve capacity. Also, the techniques may include detecting that the primary load of the datacenter exceeds the primary capacity. In addition, the techniques may include connecting the reserve generator blocks to at least one of the primary generator blocks and the primary load using a computing device switch.

Abstract: In some embodiments, the present disclosure provides an exemplary method that may include the steps of providing a computing device associated with a plurality of user; receiving output data transmitted from a target unit; analyzing the output data; transmitting a plurality of interaction commands; transmitting the plurality of interaction commands to an application or operating system; determining a plurality of identifying key words; dynamically determining a configuration screen image based on an identification of the plurality of identifying key words associated with the plurality of graphical user interface displays; automatically selecting a configuration setting associated with the plurality of interactive image elements based on the configurations screen image; and executing a plurality of ameliorative actions associated with the configuration setting.

Abstract: A method can include receiving monitoring information associated with a machine learning (ML) or artificial intelligence (AI) workload implemented by an edge compute unit of a plurality of edge compute units. Status information corresponding to a plurality of connected edge assets can be received, the plurality of edge compute units and connected edge assets included in a fleet of edge devices. A remote fleet management graphical user interface (GUI) can display a portion of the monitoring or status information for a subset of the fleet of edge devices, based on a user selection input, and can receive a user configuration input indicative of an updated configuration associated with at least one edge compute unit of the fleet. A cloud computing environment can transmit control information corresponding to the updated configuration to the at least one edge compute unit.

Abstract: A system can maintain a first data center that comprises a virtualized overlay network and virtualized volume identifiers, and store data comprising virtualized workloads. The system can determine a service level agreement associated with providing a second data center as a backup to the first data center. The system can, based on the service level agreement, divide, into a first portion of tasks and a second portion of tasks deploying the data to a secondary storage of the second data center, deploying the data to a primary storage of the second data center, and configuring the second data center with the virtualized overlay network and the virtualized volume identifiers. The system can perform the first portion of tasks before determining to restore the first data center to the second data center. The system can perform the second portion of tasks in response to determining to restore the first data center.

Abstract: A process includes determining a first degree of throttling to apply to a polling of hardware devices by a hardware processor based on a historical total utilization of the hardware processor; and determining a second degree of throttling to apply to the polling of hardware devices by the hardware processor based on a historical polling utilization of the hardware processor. The hardware processor includes, responsive to an upcoming hardware device polling cycle for the hardware processor and based on the first degree of throttling and the second degree of throttling, regulating whether the hardware processor bypasses the hardware device polling cycle or executes the hardware device polling cycle.

Abstract: The subject technology selects a candidate compute service manager from a set of instances of compute service managers to issue a query restart by selecting an execution node, the execution node being included in a particular virtual warehouse associated with the candidate compute service manager, the selecting facilitating improving utilization of cluster resources and improving query execution on the selected candidate compute service manager. The subject technology receives a notification indicating that a particular compute service manager has been quiesced. The subject technology determines a set of jobs that are not yet scheduled for execution and eligible for query retry. The subject technology determines a second set of jobs from the set of jobs to send at least another compute service manager for execution. The subject technology sends the second set of jobs to at least another compute service manager for execution.

Abstract: A method is provided comprising: monitoring, by a symbol context manager, context switch events that are generated in a virtual machine, and updating a symbol space map based on the context switch events; receiving, by the symbol context manager, a request to provide a symbol space of the virtual machine, the request being generated by a symbol database interface in response to a symbol query that is received at the symbol database interface from a debugger that is debugging the virtual machine, the symbol query being associated with a symbol that is part of the symbol space; and providing, by the symbol context manager, an indication of the symbol space of the virtual machine, the indication of the symbol space being provided based on the symbol space map.

Abstract: Implementations for adaptive context sensitive time division multiplexed scheduling and execution of tasks to be performed by a high frequency ablation system, such as an RF ablation system, are disclosed. The implementations may be effectuated in software, firmware, or both. Tasks may be categorized into categories corresponding to task priorities. Time blocks may be allocated during which execution of the tasks may be performed. The time blocks may be divided into time slots. A task may be assigned to a time slot based, at least in part, on a categorization priority of the task. Additionally, each task may be executed according to the schedule delineated by the time slots. An assignment of tasks to time slots may be adjusted based, at least in part, on data received at a high frequency ablation device of the high frequency ablation system.

Abstract: Systems and methods for optimal load distribution and data processing of a plurality of files in anti-malware solutions are provided herein. In some embodiments, the system includes: a plurality of node processors; a control processor programmed to: receiving a plurality of files used for malware analysis and training of anti-malware ML models; separating the plurality of files into a plurality of subsets of files based on byte size of each of the files, such that processing of each subset of files produces similar workloads amongst all available node processors; distributing the plurality of subsets of files amongst all available node processors such that each node processor processes its respective subset of files in parallel and within a similar timeframe as the other node processors; and receiving, by the control processor, a report of performance and/or anti-malware processing results of the subset of files performed from each node processor.

Abstract: System and method are described for copying and pasting files and folders between a client and a virtual desktop via clipboard redirection. A virtual desktop session can be established by the client on the virtual desktop. The user can copy a file or folder to the virtual desktop clipboard and a path corresponding to the file or folder can be stored in the virtual desktop clipboard in a path list. When the user ungrabs the agent or switches focus out of the virtual desktop to the client, the path list can be transferred to the client device and set into the client clipboard. Subsequently, a request can be received in the client device to paste the copied file or folder to a target location in the client device. In response to the request, the client device can retrieve the contents of the copied file or folder from the agent and the contents can be placed in the target location to complete the paste operation.

Abstract: A monitoring utility program into a software container in which a containerized virtual machine application is running. The monitoring utility program is to monitor the containerized virtual machine application running within the software container. Monitoring information regarding the containerized virtual machine application is periodically pulled from the monitoring utility program.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to relocate a compute thread, the apparatus comprising control circuitry to maintain a location of a plurality of domain access counters associated with a plurality of compute-memory domains for a first compute thread, and an execution monitor to set a first domain access counter of the plurality of domain access counters, the first domain access counter associated with a first compute-memory domain of the compute-memory domains, and relocate the first compute thread to a second compute-memory domain of the compute-memory domains in response to a comparison between a second domain access counter associated with the second compute-memory domain and the first domain access counter.